List your company

Code Generation on BigCodeBench Lite-Pro Naive Stream

44.8AccuracyReAct
35.02437.56240.142.638Jun 1, 2026

Evaluation results

MethodLinks
ReActEvaluation Pass=1st2026.0644.8——
ReActEvaluation Pass=2nd2026.0644.8——
AWMEvaluation Pass=1st2026.0644.50.3—
MEMPROBEEvaluation Pass=2nd2026.0644.5—1.4
Mem0Evaluation Pass=1st2026.0643.81—
ReMemEvaluation Pass=2nd2026.0643.8—2.1
MEMPROBEEvaluation Pass=1st2026.0643.11.7—
LangMemEvaluation Pass=2nd2026.0642.4—2.8
Mem0Evaluation Pass=2nd2026.0642.4—1.4
ReMemEvaluation Pass=1st2026.0641.73.1—
AWMEvaluation Pass=2nd2026.0641—3.5
LangMemEvaluation Pass=1st2026.0639.65.2—
DC-RSEvaluation Pass=2nd2026.0639.6—4.2
ExpRAGEvaluation Pass=1st2026.0639.65.2—
ExpRAGEvaluation Pass=2nd2026.0639.6—0
DC-RSEvaluation Pass=1st2026.0635.49.4—